Papers by Hongxu Hou

3 papers
Can Large Language Models Translate Unseen Languages in Underrepresented Scripts? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive performance in machine translation, but struggle with unseen low-resource languages.
Approach: They propose a benchmark to evaluate translation for Mongolian and Yi using linguistic resources.
Outcome: The proposed model can translate Mongolian (in traditional script) and Yi with the help of linguistic resources, but is limited in its ability to handle these languages effectively.
Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language (2026.findings-acl)

Copied to clipboard

Challenge: Current state-of-the-art LLMs exhibit clear limitations on multiple tasks, while performing well on tasks that involve contextual semantic understanding.
Approach: They propose a mouse-based benchmark to evaluate LLMs' performance on NLP tasks involving Chouxiang Language.
Outcome: The proposed benchmark evaluates the performance of LLMs on six NLP tasks involving Chouxiang Language.
Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise (P19-2)

Copied to clipboard

Challenge: Existing models for Mongolian-Chinese translation are based on recurrent, convolutional neural networks or completely eliminate recurrence connections.
Approach: They propose a adversarial training model to alleviate the UNK problem in Mongolian-Chinese machine translation by adding a screener to the model to emphasize the added Mongolian morphological noise.
Outcome: The proposed model reduces training time and improves accuracy in Mongolian-Chinese translation tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations